© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12741
    Prev
    Next
    INDEX
    Explanations

    references to organizations responsible for monitoring or oversight

    oai_token-act-pair · gpt-3.5-turbo

    the term "watchdog" and related regulatory concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kell
    -0.75
    McC
    -0.74
    uman
    -0.68
    oran
    -0.67
    esville
    -0.66
     Roof
    -0.65
    iyah
    -0.64
    uced
    -0.64
    activated
    -0.63
     Hurricanes
    -0.63
    POSITIVE LOGITS
     watchdog
    1.27
     regulator
    0.96
    mbudsman
    0.89
     outlet
    0.84
     councill
    0.82
     actionGroup
    0.81
     Monitor
    0.81
     proble
    0.79
     overse
    0.79
     probing
    0.76
    Activations Density 0.009%

    No Known Activations